lamp-onnx
API
Generated with
lamp-onnx/onnx.onnx/GraphProto

GraphProto

onnx.onnx.GraphProto
See theGraphProto companion object
final case class GraphProto(node: Seq[NodeProto], name: Option[String], initializer: Seq[TensorProto], sparseInitializer: Seq[SparseTensorProto], docString: Option[String], input: Seq[ValueInfoProto], output: Seq[ValueInfoProto], valueInfo: Seq[ValueInfoProto], quantizationAnnotation: Seq[TensorAnnotation], unknownFields: UnknownFieldSet) extends GeneratedMessage, Updatable[GraphProto]

Graphs

A graph defines the computational logic of a model and is comprised of a parameterized list of nodes that form a directed acyclic graph based on their inputs and outputs. This is the equivalent of the "network" or "graph" in many deep learning frameworks.

Value parameters

docString

A human-readable documentation for this graph. Markdown is allowed.

initializer

A list of named tensor values, used to specify constant inputs of the graph. Each initializer (both TensorProto as well SparseTensorProto) MUST have a name. The name MUST be unique across both initializer and sparse_initializer, but the name MAY also appear in the input list.

input

The inputs and outputs of the graph.

name

The name of the graph. namespace Graph

node

The nodes in the graph, sorted topologically.

quantizationAnnotation

This field carries information to indicate the mapping among a tensor and its quantization parameter tensors. For example: For tensor 'a', it may have {'SCALE_TENSOR', 'a_scale'} and {'ZERO_POINT_TENSOR', 'a_zero_point'} annotated, which means, tensor 'a_scale' and tensor 'a_zero_point' are scale and zero point of tensor 'a' in the model.

sparseInitializer

Initializers (see above) stored in sparse format.

valueInfo

Information for the values in the graph. The ValueInfoProto.name's must be distinct. It is optional for a value to appear in value_info list.

Attributes

Companion
object
Graph
Supertypes
trait Updatable[GraphProto]
trait GeneratedMessage
trait Serializable
trait Product
trait Equals
class Object
trait Matchable
class Any
Show all

Members list

Value members

Concrete methods

def addAllInitializer(`__vs`: Iterable[TensorProto]): GraphProto
def addAllInput(`__vs`: Iterable[ValueInfoProto]): GraphProto
def addAllNode(`__vs`: Iterable[NodeProto]): GraphProto
def addAllOutput(`__vs`: Iterable[ValueInfoProto]): GraphProto
def addAllValueInfo(`__vs`: Iterable[ValueInfoProto]): GraphProto
def addNode(`__vs`: NodeProto*): GraphProto
def companion: GraphProto.type
def getDocString: String
def getField(`__field`: FieldDescriptor): PValue
def getFieldByNumber(`__fieldNumber`: Int): Any
def getName: String
override def serializedSize: Int

Attributes

Definition Classes
GeneratedMessage
def toProtoString: String

Returns a human-readable ASCII format representation of this message.

Returns a human-readable ASCII format representation of this message.

The original message can be decoded from this format by using fromAscii on the companion object.

Attributes

Returns

human-readable representation of this message.

def withDocString(`__v`: String): GraphProto
def withInput(`__v`: Seq[ValueInfoProto]): GraphProto
def withName(`__v`: String): GraphProto
def withNode(`__v`: Seq[NodeProto]): GraphProto
def withUnknownFields(`__v`: UnknownFieldSet): GraphProto
def writeTo(`_output__`: CodedOutputStream): Unit

Serializes the message into the given coded output stream

Serializes the message into the given coded output stream

Attributes

Inherited methods

def productElementNames: Iterator[String]

Attributes

Inherited from:
Product
def productIterator: Iterator[Any]

Attributes

Inherited from:
Product
final def toByteArray: Array[Byte]

Serializes the message and returns a byte array containing its raw bytes

Serializes the message and returns a byte array containing its raw bytes

Attributes

Inherited from:
GeneratedMessage
final def toByteString: ByteString

Serializes the message and returns a ByteString containing its raw bytes

Serializes the message and returns a ByteString containing its raw bytes

Attributes

Inherited from:
GeneratedMessage
final def toPMessage: PMessage

Attributes

Inherited from:
GeneratedMessage
def update(ms: Lens[GraphProto, GraphProto] => () => GraphProto*): A

Attributes

Inherited from:
Updatable
final def writeDelimitedTo(output: OutputStream): Unit

Attributes

Inherited from:
GeneratedMessage
final def writeTo(output: OutputStream): Unit

Serializes the message into the given output stream

Serializes the message into the given output stream

Attributes

Inherited from:
GeneratedMessage
Generated with